Sold by: Smallest AI
Deployed on AWS
Real-time, 44.1 kHz text-to-speech with bidirectional-WebSocket streaming; fully network-isolated so text and audio never leave the account.
Overview
Lightning V3.1 Pro by Smallest AI is a low-latency, production-ready text-to-speech model built for real-time voice agents and high-volume speech generation. It produces natural, expressive speech at a native 44.1 kHz sample rate and supports synchronous HTTP, server-sent events, and WebSocket streaming. The WebSocket path accepts text incrementally and returns audio chunks as they are generated. Additional features include word-level timestamps, pronunciation dictionaries for brand names, acronyms, and technical terms, speech-rate control without pitch distortion, and multiple output formats (PCM, WAV, MP3, u-law) at sample rates from 8 kHz to 44.1 kHz for both telephony and high-fidelity playback. Its streaming pipeline is optimized for voice agents, IVR, contact centers, and other latency-sensitive workloads.
Highlights
- Low-latency text-to-speech for real-time voice agents and live calls (~120 ms time-to-first-byte under concurrent load)
- Multilingual speech synthesis in multiple languages with automatic language detection and code-switching.
- Built for conversational streaming: incremental text input over WebSocket, word-level timestamps, pronunciation dictionaries, and telephony-ready 8 kHz u-law output.
Details
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g6e.2xlarge Inference (Batch) Recommended | Model inference on the ml.g6e.2xlarge instance type, batch mode | $10.00 |
ml.g6e.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6e.2xlarge instance type, real-time mode | $10.00 |
ml.g6e.4xlarge Inference (Batch) | Model inference on the ml.g6e.4xlarge instance type, batch mode | $10.00 |
ml.g6e.4xlarge Inference (Real-Time) | Model inference on the ml.g6e.4xlarge instance type, real-time mode | $10.00 |
ml.g6e.8xlarge Inference (Real-Time) | Model inference on the ml.g6e.8xlarge instance type, real-time mode | $10.00 |
ml.g6e.16xlarge Inference (Real-Time) | Model inference on the ml.g6e.16xlarge instance type, real-time mode | $10.00 |
ml.g7e.2xlarge Inference (Real-Time) | Model inference on the ml.g7e.2xlarge instance type, real-time mode | $40.00 |
ml.g7e.4xlarge Inference (Real-Time) | Model inference on the ml.g7e.4xlarge instance type, real-time mode | $40.00 |
ml.g7e.8xlarge Inference (Real-Time) | Model inference on the ml.g7e.8xlarge instance type, real-time mode | $40.00 |
ml.p5.4xlarge Inference (Real-Time) | Model inference on the ml.p5.4xlarge instance type, real-time mode | $35.00 |
Vendor refund policy
N/A
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
- Text to speech Model, English and Hindi
Additional details
Inputs
- Summary
Model input summary application/json. A UTF-8 JSON body with text (required), voice_id, and optional model, language, sample_rate, speed, output_format, and pronunciation_dicts.
The batch link is the synchronous endpoint page. It shows POST https://api.smallest.ai/waves/v1/tts , which takes text and voice_id and returns binary audio. The real-time link is the WebSocket reference for /waves/v1/tts/live. The SSE page says the same URL serves the WebSocket endpoint, accepting a WebSocket upgrade for streaming-text scenarios such as LLM token streams and live captioning. I found the WebSocket page linked from the SSE reference but didn’t open it directly, so click through once before you paste it in. If you want to point at SSE instead, use https://docs.smallest.ai/models/api-reference/text-to-speech/synthesize-speech-sse .
- Input MIME type
- application/json
https://docs.smallest.ai/models/api-reference/text-to-speech/stream-speech-web-socket
https://docs.smallest.ai/models/api-reference/text-to-speech/synthesize-speech
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Waves TTS by Smallest.ai delivers real-time, multilingual text-to-speech for global, production-grade voice applications - powered by our state-of-the-art Lightning V2 engine, benchmarked for the fastest, most natural speech synthesis
Lightning ASR delivers real-time, multilingual speech-to-text for production voice applications - optimized for sub-300ms latency, high accuracy, and robust to noise and accents.
bidirectional-WebSocket streaming; diarization and PII redaction built in; fully network-isolated so audio never leaves the account.
Smallest AI's Voice AI Platform brings our entire voice stack to AWS Marketplace under one listing with consolidated billing. Build and deploy no-code Atoms voice and chat agents that automate support, sales, and operations with end-to-end conversation handling in 20+ languages, or procure the underlying models directly: Lightning text-to-speech (broadcast-quality 44.1 kHz audio, ~100 ms latency, instant voice cloning, 15 languages) and Pulse speech-to-text (~64 ms first transcript, diarization, PII/PCI redaction, 38 languages). Subscribe once, use any mix of agents, TTS, and STT, and see all usage on a single AWS invoice with usage-based pricing. Enterprise-grade latency, SOC 2 Type II and PCI-DSS, flexible AWS-region deployment with data residency and in-VPC options, and private offers for committed-use deals.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.